Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Andytoizer/gtm-brain-builder --skill customer-icp-agentgit clone --depth 1 https://github.com/Andytoizer/gtm-brain-builderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/andytoizer/gtm-brain-builder/customer-icp-agent)<a href="https://agentmods.dev/skills/andytoizer/gtm-brain-builder/customer-icp-agent"><img src="https://agentmods.dev/badge/skills/andytoizer/gtm-brain-builder/customer-icp-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/andytoizer/gtm-brain-builder/customer-icp-agent"><img src="https://agentmods.dev/badge/skills/andytoizer/gtm-brain-builder/customer-icp-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00241 |
| Opus 5 | $0.00018 | $0.00120 |
| Sonnet 5 | $0.00007 | $0.00048 |
| Haiku 4.5 | $0.00004 | $0.00024 |
Grade A, and why
customer-icp-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Customer ICP Agent
Owns customers/ and icp/.
Inputs
- Revenue/billing for commercial value.
- CRM for lifecycle, deal, source, owner, and company context.
- Product DB/analytics for usage and activation.
- Support, customer Slack, email, and calls for pain and success context.
- Operator review for meaning and prioritization.
Outputs
customers/customer-list.mdcustomers/proof-approval.mdcustomers/top-customers.mdcustomers/feedback.mdicp/best-customers.mdicp/our-icp.mdicp/personas.md
Rules
- Customer name, logo, use case, metric, quote, screenshot, and case study are separate proof approvals.
- Clean aliases before using customer names as public proof.
- Do not derive ICP from one source alone.
- Ask Grill-me before promoting best-customer patterns.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 34 lines · 36 tokens per session scan A 71fc4bf328be
customer-icp-agent is a skill published in the GitHub repository Andytoizer/gtm-brain-builder (8 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 241 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
open-cmo
Real-world growth & GTM know-how from 16 tech-company experts. Covers: paid ads (Google/Meta/LinkedIn), out-of-home & ABM, channel selection, PLG→Enterprise, SEO/GEO, programmatic SEO, launches & Product Hunt, pricing & monetization for AI products, ad creative strategy, organic and viral growth, and growth…
content-atomizer
Repurposes single content pieces into multiple formats for maximum distribution while maintaining brand voice. This skill should be used when maximizing ROI from pillar content, filling content calendars efficiently, reaching audiences across multiple platforms, or when creating original content for every channel…
orchestrator
Diagnoses marketing needs and sequences appropriate skills for comprehensive campaigns. This skill should be used when unsure which marketing skill to use, planning multi-step marketing campaigns, creating integrated marketing strategies, or when a project spans multiple marketing disciplines.
sales-orchestrator
Diagnoses sales needs and sequences appropriate skills for comprehensive deal execution. Use this skill when unsure which sales skill to use, planning multi-step deal strategies, coaching reps on process, or coordinating complex sales motions.
keyword-research
Content planning framework using the 6 Circles Method for identifying high-value topics without paid SEO tools. This skill should be used when building content strategy from scratch, planning quarterly content calendars, finding content gaps, or when unsure what to write about next.
seo-content
Creates search-optimized articles that rank well and read naturally for humans. This skill should be used when writing blog posts, pillar content, guides, or any content where organic search traffic is a goal - balancing search engine requirements with genuine reader value.